[Usage]: How can I convert gpt-oss-120b to tensorrt checkpoint to build the engines and execute with trt backend in tensorrt-llm?

[alrolo3]

System Info

System Information:

Detailed output:

+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.274.02             Driver Version: 535.274.02   CUDA Version: 13.0     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA A100-SXM4-80GB          On  | 00000000:07:00.0 Off |                    0 |
| N/A   31C    P0              69W / 400W |  37711MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   1  NVIDIA A100-SXM4-80GB          On  | 00000000:0F:00.0 Off |                    0 |
| N/A   30C    P0              71W / 400W |  34993MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   2  NVIDIA A100-SXM4-80GB          On  | 00000000:47:00.0 Off |                    0 |
| N/A   30C    P0              66W / 400W |  34993MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   3  NVIDIA A100-SXM4-80GB          On  | 00000000:4E:00.0 Off |                    0 |
| N/A   30C    P0              70W / 400W |  32969MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   4  NVIDIA A100-SXM4-80GB          On  | 00000000:87:00.0 Off |                    0 |
| N/A   37C    P0              70W / 400W |  34993MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   5  NVIDIA A100-SXM4-80GB          On  | 00000000:90:00.0 Off |                    0 |
| N/A   36C    P0              70W / 400W |  34993MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   6  NVIDIA A100-SXM4-80GB          On  | 00000000:B7:00.0 Off |                    0 |
| N/A   35C    P0              70W / 400W |  32969MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   7  NVIDIA A100-SXM4-80GB          On  | 00000000:BD:00.0 Off |                    0 |
| N/A   37C    P0              72W / 400W |  16757MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
                                                                                         
+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
+---------------------------------------------------------------------------------------+
Python 3.12.3
Name: tensorrt_llm
Version: 1.2.0rc5```


### How would you like to use TensorRT-LLM

How can I convert gpt-oss-120b to tensorrt checkpoint to build the engines and execute with trt backend in tensorrt-llm? 




### Before submitting a new issue...

- [x] Make sure you already searched for relevant issues, and checked the [documentation](https://nvidia.github.io/TensorRT-LLM/) and [examples](https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples) for answers to frequently asked questions.

[karljang]

Hi @alrolo3,
I regret to inform you that GPT-OSS-120B currently does not support the TensorRT backend. It only supports the PyTorch backend.
Additionally, it requires the Blackwell architecture, which means that the A100-SXM4-80GB (Ampere architecture) is not compatible.

For reference,:

• Supported Models
• Deployment Guide for GPT-OSS on TensorRT-LLM - Blackwell Hardware